netscan: stop the scan wedging, and stop it overstating the LAN

The results channel was sized by the number of hosts while each worker
sends once per open port, so a subnet with more open ports than
addresses filled the buffer and blocked a worker forever. Nothing drains
the channel until wg.Wait returns and the sends have no ctx.Done case,
so the calling turn hung for the life of the process. Size it by probes.

Three more claims the scanner could not back. MaxHosts was spent in
order, so the second of two configured subnets got two addresses out of
254 with nothing logged. A run cut short by the cap or the deadline came
back indistinguishable from a complete one, and the shipped defaults
never fit the budget, so every scan was silently truncated at the top of
the range. Scan now reports truncation, targets are taken round-robin,
and the default rate and the budget are consistent with a /24.

The spoken reply read dotted quads out loud on the voice path. It now
says how many devices and what shape, and writes the address list as a
note, which is also the only record that Maven put packets on the LAN.
The network noun is matched whole so posetil is not a scan, the rate has
a stated ceiling, and a repeat question inside two minutes reuses the
answer.

Both query sources claimed the turn when the capability was off, which
let an unconfigured scanner and an unconfigured house swallow questions
that used to reach recall. Both now fall through.
Found in review of #81 and #80.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX

cmd/mavend/actions_query.go

@@ -295,9 +295,13 @@ func (h *reactiveHandler) queryHome(ctx context.Context, t *queryTurn) (string,
 		return "", false
 	}
 	if h.home == nil {
-		// Claim the turn rather than fall through: "дом не подключён" is true,
-		// and letting general knowledge answer would be an invented house.
-		return "дом не подключён — я его не вижу.", true
+		// Fall through rather than claim the turn. A capability that is off
+		// must not change what an unconfigured box answers: "какая температура
+		// в доме?" on a Maven with no smarthome block reached recall before
+		// this source existed, and a stored fact is a better answer than
+		// "дом не подключён" from a house that was never configured. The
+		// unreachable case is different and homeSummary covers it.
+		return "", false
 	}
 	ctxH, cancel := context.WithTimeout(ctx, 10*time.Second)
 	defer cancel()
@@ -313,9 +317,9 @@ func (h *reactiveHandler) queryNetwork(ctx context.Context, t *queryTurn) (strin
 		return "", false
 	}
 	if h.netscan == nil {
-		// Claim the turn: "сканирование не настроено" is true, and general
-		// knowledge would answer with an invented list of devices.
-		return "сканирование сети не настроено.", true
+		// Fall through, same as queryHome: an unconfigured scanner must not
+		// swallow "сколько устройств в сети?" before recall has looked.
+		return "", false
 	}
 	return h.netscan.scanSummary(ctx)
 }

cmd/mavend/netscan.go

@@ -5,20 +5,33 @@ import (
 	"fmt"
 	"log"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/kami/maven/internal/config"
+	"github.com/kami/maven/internal/ipc"
 	"github.com/kami/maven/internal/netscan"
 )
 
 // scanBudget — the whole spoken scan, end to end. A voice turn that takes
 // longer than this has already failed as a turn, so the scan returns whatever
 // it found rather than keeping him waiting.
-const scanBudget = 20 * time.Second
+//
+// It has to be consistent with the shipped defaults or every scan is truncated:
+// a /24 at four ports is 1016 probes, which at netscan.DefaultRate of 100 a
+// second is a little over ten seconds plus the tail dials. 30s leaves room for
+// that without pretending a slower rate would fit.
+const scanBudget = 30 * time.Second
 
-// scanReadOut — how many hosts she names out loud. The rest are a count: a
-// spoken list of twenty IP addresses is not an answer.
-const scanReadOut = 6
+// scanCacheTTL — how long a scan answer is reused. Two questions in a row used
+// to be two full sweeps of the LAN, up to a thousand connections each. The
+// network does not change on the scale of a follow-up question, and the cheapest
+// packet is the one not sent.
+const scanCacheTTL = 2 * time.Minute
+
+// scanReadOut — how many hosts go into the written record's first lines before
+// it says "и ещё N". Nothing reads addresses out loud; see scanSummary.
+const scanReadOut = 20
 
 // netWiring — the LAN scanner, when the `netscan` block is enabled. nil ⇒ Maven
 // never puts a discovery packet on the network.
@@ -30,10 +43,21 @@ const scanReadOut = 6
 type netWiring struct {
 	scanner *netscan.Scanner
 	subnets []string
+	// api — where the address list is WRITTEN. The spoken answer is a count
+	// and a shape, so the detail has to land somewhere readable; a note under
+	// source "scan:lan" puts it on /history and, through the intake decorator,
+	// on /events. It is also the only record that Maven put packets on the LAN
+	// at all. nil ⇒ nothing is written, which is what the tests use.
+	api ipc.CoreAPI
+	now func() time.Time
+
+	mu       sync.Mutex
+	cached   netscan.Result
+	cachedAt time.Time
 }
 
 // wireNetScan builds the scanner. nil unless the block is enabled and valid.
-func wireNetScan(cfg *config.Config) *netWiring {
+func wireNetScan(cfg *config.Config, api ipc.CoreAPI) *netWiring {
 	nc, ok := cfg.NetScanner()
 	if !ok {
 		return nil
@@ -45,29 +69,125 @@ func wireNetScan(cfg *config.Config) *netWiring {
 		log.Printf("netscan: not wired: %v", err)
 		return nil
 	}
-	return &netWiring{scanner: netscan.New(nc), subnets: nc.Subnets}
+	return &netWiring{scanner: netscan.New(nc), subnets: nc.Subnets, api: api, now: time.Now}
 }
 
-// scanSummary answers "какие устройства в сети?" in one line.
+// scan runs a scan, or reuses one younger than scanCacheTTL.
+func (w *netWiring) scan(ctx context.Context) (netscan.Result, error) {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+	now := w.now()
+	if !w.cachedAt.IsZero() && now.Sub(w.cachedAt) < scanCacheTTL {
+		return w.cached, nil
+	}
+	scanCtx, cancel := context.WithTimeout(ctx, scanBudget)
+	defer cancel()
+	res, err := w.scanner.Scan(scanCtx)
+	if err != nil {
+		return res, err
+	}
+	w.cached, w.cachedAt = res, now
+	// Written on a fresh scan only: the record is a trace of packets going out,
+	// so a cached answer must not forge a second one.
+	w.writeScanRecord(ctx, res)
+	return res, nil
+}
+
+// scanSummary answers "какие устройства в сети?" in one spoken line.
+//
+// It does NOT read addresses out. This is the query path, so the reply goes to
+// piper as well as to /chat, and "192.168.1.1 (80, 443); 192.168.1.14 (22)" is
+// a digit stream nobody can follow through a speaker. She says how many and
+// what shape they are; the addresses go into a note (see writeScanRecord).
 func (w *netWiring) scanSummary(ctx context.Context) (string, bool) {
 	if w == nil {
 		return "", false
 	}
-	ctx, cancel := context.WithTimeout(ctx, scanBudget)
-	defer cancel()
-	hosts, err := w.scanner.Scan(ctx)
+	res, err := w.scan(ctx)
 	if err != nil {
 		log.Printf("netscan: scan: %v", err)
 		return "не получилось просканировать сеть.", true
 	}
-	if len(hosts) == 0 {
-		return "в сети никого не нашла.", true
+	// A truncated run is not a statement about the LAN. Saying "нашла 6
+	// устройств" after stopping two thirds of the way through the range is a
+	// false claim, and the addresses at the end are the ones that go missing.
+	tail := ""
+	if res.Truncated {
+		tail = ", но успела посмотреть не всю сеть"
 	}
-	shown := hosts
+	if len(res.Hosts) == 0 {
+		return "в сети никого не нашла" + tail + ".", true
+	}
+	out := fmt.Sprintf("нашла %d %s", len(res.Hosts), hostWord(len(res.Hosts)))
+	if shape := scanShape(res.Hosts); shape != "" {
+		out += ", " + shape
+	}
+	out += tail
+	if w.api != nil {
+		out += ". список записала"
+	}
+	return out + ".", true
+}
+
+// scanShape describes the hosts by what they answer on, which is the part of
+// the answer that carries meaning out loud: "два с вебом" says more about the
+// flat than four octets do.
+func scanShape(hosts []netscan.Host) string {
+	var web, ssh, quiet int
+	for _, h := range hosts {
+		hasWeb, hasSSH := false, false
+		for _, p := range h.Ports {
+			switch p {
+			case 80, 443, 8080:
+				hasWeb = true
+			case 22:
+				hasSSH = true
+			}
+		}
+		if hasWeb {
+			web++
+		}
+		if hasSSH {
+			ssh++
+		}
+		// No open port at all: seen only through the ARP cache.
+		if len(h.Ports) == 0 {
+			quiet++
+		}
+	}
+	var parts []string
+	if web > 0 {
+		parts = append(parts, fmt.Sprintf("%d с вебом", web))
+	}
+	if ssh > 0 {
+		parts = append(parts, fmt.Sprintf("%d с ssh", ssh))
+	}
+	if quiet > 0 {
+		parts = append(parts, fmt.Sprintf("%d молча", quiet))
+	}
+	if len(parts) == 0 {
+		return ""
+	}
+	return "из них " + strings.Join(parts, ", ")
+}
+
+// writeScanRecord stores the address list as a note. This is both where the
+// detail becomes readable and the only trace that a scan happened at all: a
+// scan is a read, but "when did she last put packets on the LAN" deserves an
+// answer.
+func (w *netWiring) writeScanRecord(ctx context.Context, res netscan.Result) {
+	if w.api == nil {
+		return
+	}
+	head := fmt.Sprintf("сканирование сети: %d %s", len(res.Hosts), hostWord(len(res.Hosts)))
+	if res.Truncated {
+		head += " (не вся сеть)"
+	}
+	lines := []string{head, "подсети: " + strings.Join(w.subnets, ", ")}
+	shown := res.Hosts
 	if len(shown) > scanReadOut {
 		shown = shown[:scanReadOut]
 	}
-	parts := make([]string, 0, len(shown))
 	for _, h := range shown {
 		s := h.Addr
 		if len(h.Ports) > 0 {
@@ -77,13 +197,17 @@ func (w *netWiring) scanSummary(ctx context.Context) (string, bool) {
 			}
 			s += " (" + strings.Join(ps, ", ") + ")"
 		}
-		parts = append(parts, s)
+		if h.MAC != "" {
+			s += " " + h.MAC
+		}
+		lines = append(lines, s)
 	}
-	out := fmt.Sprintf("нашла %d %s: %s", len(hosts), hostWord(len(hosts)), strings.Join(parts, "; "))
-	if len(hosts) > len(shown) {
-		out += fmt.Sprintf(" и ещё %d", len(hosts)-len(shown))
+	if len(res.Hosts) > len(shown) {
+		lines = append(lines, fmt.Sprintf("и ещё %d", len(res.Hosts)-len(shown)))
+	}
+	if _, err := w.api.WriteNote(ctx, w.now(), strings.Join(lines, "\n"), nil, "scan:lan"); err != nil {
+		log.Printf("netscan: write scan note: %v", err)
 	}
-	return out + ".", true
 }
 
 // hostWord — Russian counts inflect the noun: 1 устройство, 2-4 устройства,
@@ -111,13 +235,25 @@ func isNetworkQuery(u string) bool {
 	if s == "" {
 		return false
 	}
+	// Whole tokens for the network nouns: the bare substring "сети" is inside
+	// "посетил", so "сколько машин я посетил?" used to read as a request to
+	// scan the LAN. The prefix forms below are stems that have no such
+	// collisions.
 	network := false
-	for _, w := range []string{"в сети", "в сетке", "сеть", "сети", "локальн", "wifi", "wi-fi", "вайфай"} {
-		if strings.Contains(s, w) {
+	for _, w := range []string{"сеть", "сети", "сетке", "сетку"} {
+		if homeWord(s, w) {
 			network = true
 			break
 		}
 	}
+	if !network {
+		for _, w := range []string{"локальн", "wifi", "wi-fi", "вайфай"} {
+			if strings.Contains(s, w) {
+				network = true
+				break
+			}
+		}
+	}
 	if !network {
 		return false
 	}

cmd/mavend/netscan_test.go

@@ -2,10 +2,14 @@ package main
 
 import (
 	"context"
+	"net"
+	"strconv"
 	"strings"
 	"testing"
+	"time"
 
 	"github.com/kami/maven/internal/config"
+	"github.com/kami/maven/internal/ipc"
 )
 
 func TestWireNetScanOffUnlessEnabled(t *testing.T) {
@@ -23,7 +27,7 @@ func TestWireNetScanOffUnlessEnabled(t *testing.T) {
 		}},
 	} {
 		t.Run(name, func(t *testing.T) {
-			if w := wireNetScan(cfg); w != nil {
+			if w := wireNetScan(cfg, nil); w != nil {
 				t.Fatal("the scanner must not wire for this config")
 			}
 		})
@@ -36,7 +40,7 @@ func TestWireNetScanOffUnlessEnabled(t *testing.T) {
 
 	ok := wireNetScan(&config.Config{NetScan: &config.NetScanConfig{
 		Subnets: []string{"192.168.1.0/24"}, Enabled: true,
-	}})
+	}}, nil)
 	if ok == nil {
 		t.Fatal("a valid enabled block should wire")
 	}
@@ -50,7 +54,7 @@ func TestScanSummaryOnAnEmptyRange(t *testing.T) {
 		// Port 1 on loopback: nothing listens and the connection is refused
 		// immediately, so the scan is fast and touches only this machine.
 		Subnets: []string{"127.0.0.1/32"}, Ports: []int{1}, Rate: 1000, Enabled: true,
-	}})
+	}}, nil)
 	if w == nil {
 		t.Fatal("wireNetScan returned nil")
 	}
@@ -109,3 +113,59 @@ func TestIsNetworkQuery(t *testing.T) {
 		}
 	}
 }
+
+// notingAPI counts the notes a scan writes, and remembers the last one.
+type notingAPI struct {
+	ipc.CoreAPI
+	n    int
+	last string
+}
+
+func (a *notingAPI) WriteNote(_ context.Context, _ time.Time, text string, _ []float32, _ string) (int64, error) {
+	a.n++
+	a.last = text
+	return int64(a.n), nil
+}
+
+// The spoken answer must not be a list of IP addresses. It goes to piper as
+// well as to /chat, and six dotted quads read out as a digit stream is not an
+// answer anybody can use. The addresses belong in the written record.
+func TestScanSummarySpeaksACountAndWritesTheAddresses(t *testing.T) {
+	ln, err := net.Listen("tcp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer ln.Close()
+	_, portStr, _ := net.SplitHostPort(ln.Addr().String())
+	port, _ := strconv.Atoi(portStr)
+
+	api := &notingAPI{}
+	w := wireNetScan(&config.Config{NetScan: &config.NetScanConfig{
+		Subnets: []string{"127.0.0.1/32"}, Ports: []int{port}, Rate: 1000, Enabled: true,
+	}}, api)
+	if w == nil {
+		t.Fatal("wireNetScan returned nil")
+	}
+	out, claimed := w.scanSummary(context.Background())
+	if !claimed {
+		t.Fatal("the summary did not claim the turn")
+	}
+	if strings.Contains(out, "127.0.0.1") || strings.Contains(out, portStr) {
+		t.Errorf("the spoken reply reads addresses out loud: %q", out)
+	}
+	if !strings.Contains(out, "нашла 1 устройство") {
+		t.Errorf("reply = %q, want a count", out)
+	}
+	if api.n != 1 {
+		t.Fatalf("wrote %d notes, want 1", api.n)
+	}
+	if !strings.Contains(api.last, "127.0.0.1") {
+		t.Errorf("the written record has no addresses: %q", api.last)
+	}
+
+	// A follow-up question inside the TTL reuses the answer: two questions in
+	// a row must not be two sweeps of the LAN.
+	if _, _ = w.scanSummary(context.Background()); api.n != 1 {
+		t.Errorf("a repeat question rescanned and rewrote the record (%d notes)", api.n)
+	}
+}

cmd/mavend/voicewire.go

@@ -166,7 +166,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
 	}
 	// The LAN scanner (Vikunja #257): a read, bounded to the configured
 	// subnets and rate-limited. Off unless the `netscan` block is enabled.
-	w.netscan = wireNetScan(cfg)
+	w.netscan = wireNetScan(cfg, coreAPI)
 	matcher := tool.NewMatcher(coreAPI)
 
 	// ----- weather provider (Open-Meteo when configured, Stub otherwise) -----